PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation

arXiv:2603.17356v3 Announce Type: replace Abstract: Drug recommendation requires a deep understanding of individual patient context, especially for complex conditions like Parkinson's disease. While LLMs possess broad medical knowledge, they fail to capture the subtle nuances of actual prescribing patterns. Existing RAG methods also struggle with these complexities because guideline-based retrieval remains too generic and similar-patient retrieval often replicates majority patterns without accounting for the unique clinical nuances of individual patients. To bridge this gap, we propose PACE-RAG (Patient-Aware Contextual and Evidence-Constrained RAG). Rather than directly copying frequent medications from retrieved patients, PACE-RAG personalizes recommendations by first extracting patient-specific clinical features, retrieving cases around these features, and then refining the final prescription using the patient's current symptoms, active medication history, and focus-specific prescribing tendencies. By analyzing treatment patterns tailored to specific clinical features, PACE-RAG generates patient-specific medication recommendations along with an explainable clinical summary. PACE-RAG achieved the strongest performance among the evaluated inference-only LLM-based methods, reaching F1 scores of 80.84% and 47.22% on the Parkinson's disease and MIMIC-IV cohorts, respectively. Our code is available at: https://github.com/ChaeYoungHuh/PACE-RAG.

Related

• Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
• LTR-ICD: A Ranking-Aware Framework for Automatic ICD Coding
• CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space
• What Survives Into Context: A Diagnostic for Budget-Constrained Multi-Hop RAG and When Submodular Evidence Packing Improves It

Source: arXiv cs.CL | 2026-09-01